Dark-Scarlett-v1.0-26B-A4B EXL3 6.10bpw HB8

This repository contains an EXL3 quantization of ReadyArt/Dark-Scarlett-v1.0-26B-A4B for ExLlamaV3.

Quantization

  • Model: ReadyArt/Dark-Scarlett-v1.0-26B-A4B
  • Quantizer: exllamav3-1.4.4
  • Format: exl3
  • Bits per weight: 6.10
  • Head bits: 8
  • Calibration: 250 rows, 2048 columns
  • Output scales: always
  • Codebook: mul1
  • Files: 3 sharded .safetensors files

Compatibility

For the original model card and non-quantized weights, see ReadyArt/Dark-Scarlett-v1.0-26B-A4B.

Original Model Card: Dark-Scarlett-v1.0-26B-A4B

Dark Scarlett 26B A4B

⚡ v1.0

Passion ignited. Boundaries dissolved.

🧠 Thinking Enable: Use chat_template_kwargs: {"enable_thinking": true, "reasoning_effort": "medium"} in SillyTavern. ✦ 🔞 NSFW ERP Uncensored Roleplay Gemma-4 Adult Unaligned ✦ Content Advisory: Mature Themes / Adult Interactions — Intended for mature audiences only. ✦

✦ Core Capabilities ✦

Optimized for immersive adult narrative experiences

6000+ Kink Prompts (In Generator) 100% Uncensored M→F Perspective ⟡ Gemma 4 Based ✦ 🌹 What Is Dark Scarlett?

Inspired by the spirit of Melody1437, though trained on a distinct dataset, Dark Scarlett-26B refines the core architecture with specialized scenario prompts to enhance depth and responsiveness. This model focuses on delivering a cohesive narrative experience with a distinct perspective.

Core Inspiration Melody1437 Spirit Distinct Dataset ⟡ Result Dark Scarlett ⚠️ Perspective Note: Training data strictly follows a Male (User) → Female (AI) perspective for consistent roleplay dynamics.
  • 🧠 Core Heritage: Captures the spirit of Melody1437 with diversified scenario prompts
  • 🎭 Group Chat Support: Includes some training for dynamic group chat interactions
  • 🎯 Perspective: Optimized for Male User → Female AI interactions
  • 📖 Narrative Flow: Improved context retention with longer conversation threads in select scenarios
🧬 Synthetic Life Engine

Dataset generated using our advanced Character Engine and Emotional Engine, creating genuine life and emotional resonance in every interaction.

🎭 Character Engine

Ensures consistent personality traits, speech patterns, and behavioral logic across all contexts. Characters remain true to themselves throughout.

💓 Emotional Engine

Injects dynamic emotional states into responses, creating depth and realistic reactions that breathe life into every exchange.

✨ Quality Refinement

Automated detection and rewriting of repetitive phrases ensures fresh, high-quality dialogue in every turn.

💬 Dialogue Integrity

Advanced quote normalization ensures balanced dialogue markers, preventing formatting errors and maintaining immersion.

🧠 Training Details & Parameters

Fine-tuned using LoRA (Low-Rank Adaptation) for efficient and targeted weight adjustment, preserving the base model's capabilities while imprinting new behavioral patterns.

🔢 Epochs

2

Full passes through the training dataset for thorough learning

📐 LoRA Rank

32

Optimized rank for balanced adaptation and efficiency

ParameterValue
Training MethodLoRA (Low-Rank Adaptation)
LoRA Rank (r)32
Epochs2
Trained LayersText layers only
FeatureGroup Chat Support
  • 🎯 Method: LoRA fine-tuning for parameter-efficient adaptation, preserving base knowledge while imprinting new behaviors
  • ⚡ Efficiency: Only a fraction of parameters updated, keeping the model lean and responsive
  • 🎭 Result: Maintains coherence while exhibiting the desired personality traits and interaction style
🔮 Training Process

Model weights subjected to iterative refinement during data creation. Each conversation underwent multiple checks for stability and alignment.

  • 🔄 Multi-Turn Generation: Conversations built turn-by-turn for natural context flow
  • 🛡️ Refusal Filtering: Automated systems detected and removed unwanted refusals
  • 🧹 Slop Cleaning: Undesirable phrases identified and rewritten by dedicated assistant models
  • 🎪 Group Chat Training: Includes some training data focused on multi-user group dynamics
📚 Dataset Overview

Model trained on a specialized adult-oriented roleplay dataset with diverse scenarios and emotional contexts, inspired by the spirit of Melody1437, though distinct in composition.

  • 🔞 Content Rating: Strictly 18+ (Adults Only)
  • 📊 Dataset Size: Currently contains 12,211 specialized prompts.
  • 📝 Conversation Depth: Portions include extended conversations for enhanced roleplay continuity.
  • 🎭 Focus: Mature themes, immersive roleplay, uncensored dialogue
  • 👥 Perspective: Male (User) → Female (AI)
  • 🧹 Formatting: Removed Em dashes, asterisks, and markdown formatting from the dataset for cleaner output.
📜 Version Notes
  • ⚠️ Content Warning: This model can generate mature content. Use responsibly.
  • 📉 Data Limitations: Trained on a curated dataset (12,211 prompts); performance may vary.
  • 🧹 Clean Output: Reasoning tags, Em dashes, asterisks, and markdown formatting stripped for cleaner roleplay
  • 🔀 Core Identity: Trained on the spirit of Melody1437, but utilizes a unique dataset
  • 🎪 Feature: Includes some training for group chat scenarios
⚙️ Configuration

🎛️ Sampler Settings

Recommended parameters for optimal output

0.92 Top-P 1.0 Temperature 0 Freq Pen 0 Presence Pen

📦 GGUF Quantizations

Available formats for local inference

  • Q4_K_MDecent Quality
  • Q5_K_MRecommended
  • Q6_KHigh Quality
  • Q8_0Near Lossless
⬇ View Repository 💖 Credits
  • GECFDO — Dataset Generation
  • FrenzyBiscuit — Fine-Tuning & Dataset Creation
⟡

🔖 License & Usage

⚠️ Usage Agreement: By using this model, you accept all terms and conditions.
  • 📜 Built upon the Apache 2.0 license
  • 🛡️ You accept full responsibility for all outputs generated
  • 🔞 You confirm you are at least 18 years old
  • 🌍 Creators bear no responsibility for how the model is used
  • 🏡 For personal use only (non-profit/non-commercial) to the extent legally allowed
Apache 2.0 Personal Use 18+ Content NSFW